Research map / Reinforcement learning / Offline RL
What Matters for Batch Online Reinforcement Learning in Robotics?
Perry Dong, Suvir Mirchandani, Dorsa Sadigh, Chelsea Finn
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use value-based RL (Q-function guidance) instead of IL or filtered-IL (ablation) | batch online RL · 6 simulated manipulation tasks | normalized return | Improved |
| use filtered-IL instead of vanilla IL (ablation) | batch online RL · 6 simulated manipulation tasks | normalized return | Mixed |
| use implicit policy extraction (best-of-N by Q) instead of explicit AWR extraction (ablation) | batch online RL · 6 simulated manipulation tasks | normalized return after iterations | Improved |
| use explicit AWR extraction (initial performance only) (ablation) | batch online RL · 6 simulated manipulation tasks | initial normalized return | Improved |
| use diffusion policy instead of Gaussian policy (ablation) | value-based batch online RL · 6 simulated manipulation tasks | normalized return | Improved |
| add implicit extraction to Gaussian policy (ablation) | value-based batch online RL · 6 simulated manipulation tasks | normalized return | Improved |
| increase rollouts per iteration (ablation) | value-based RL · 6 simulated tasks | normalized return | Improved |
| add Ornstein-Uhlenbeck temporally-correlated noise to rollouts (ablation) | batch online RL recipe · 6 simulated tasks | normalized return | Improved |
| add temporally-correlated noise (ablation) | batch online RL recipe · data scaling | scaling with data | No clear effect |
| use recipe instead of filtered-IL on real robot | batch online RL · Real-world Tape task | success rate: 30% improvement over initial policy in 3 iterations | Improved |
| use steering baseline (Q-guided sampling from fixed policy) | batch online RL · Real-world Tape task | success rate | Hurt |
Closest papers by meaning
- Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model (ICLR 2025 · similarity 0.90)
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning (ICLR 2024 · similarity 0.89)
- Blending Imitation and Reinforcement Learning for Robust Policy Improvement (ICLR 2024 · similarity 0.89)
- Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization (ICLR 2024 · similarity 0.89)
- Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data (AAAI 2025 · similarity 0.89)
- A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
